A radiomics method to classify microcalcification clusters in digital breast tomosynthesis.

PURPOSE Digital breast tomosynthesis (DBT) is becoming increasingly used in clinical practice. In DBT, the microcalcification clusters may span across multiple slices, which makes it difficult for radiologists to directly assess these distributed clusters for diagnosis. We investigated a radiomics method to classify microcalcification clusters in DBT based on a semi-automatic segmentation process. METHODS We performed a retrospective study on a cohort of 275 patients (including 79 benign and 196 malignant cases) with a total of 550 DBT volumes. Our method consisted of three steps. The initial step was to semi-automatically segment the microcalcification clusters. Then, radiomics features were extracted from the initially segmented microcalcification clusters. Finally, the benign and malignant microcalcification clusters were differentiated by the random forest (RF) classifier using selected subset features. The radiomics models were evaluated both on view-based and case-based modes with features selected from different domains. The receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) were used to evaluate the classification performance. RESULTS 26 key features were selected from a total of 170 radiomics features and these features show promising classification performance. The highest AUC was 0.834 for view-based mode and 0.868 for case-based mode when using features selected from the 3D domain. The 2D domain radiomics features showed a statistically similar performance to the 3D features (p>0.05). CONCLUSION Radiomics models can provide encouraging performance in classification between malignant and benign microcalcification clusters which are semi-automatically segmented in DBT.

[1]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[2]  Berkman Sahiner,et al.  Computer-aided detection of clustered microcalcifications in multiscale bilateral filtering regularized reconstructed digital breast tomosynthesis volume. , 2014, Medical physics.

[3]  E. Halpern,et al.  Assessing radiologist performance using combined digital mammography and breast tomosynthesis compared with digital mammography alone: results of a multicenter, multireader trial. , 2013, Radiology.

[4]  Hui Li,et al.  Transfer Learning From Convolutional Neural Networks for Computer-Aided Diagnosis: A Comparison of Digital Breast Tomosynthesis and Full-Field Digital Mammography. , 2019, Academic radiology.

[5]  Jing Li,et al.  SD-CNN: a Shallow-Deep CNN for Improved Breast Cancer Diagnosis , 2018, Comput. Medical Imaging Graph..

[6]  Ioannis Sechopoulos,et al.  Optimization of the acquisition geometry in digital tomosynthesis of the breast. , 2009, Medical physics.

[7]  J. Ji,et al.  Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer , 2019, Annals of oncology : official journal of the European Society for Medical Oncology.

[8]  Heang-Ping Chan,et al.  Digital breast tomosynthesis: observer performance of clustered microcalcification detection on breast phantom images acquired with an experimental system using variable scan angles, angular increments, and number of projection views. , 2014, Radiology.

[9]  David Gur,et al.  Digital Mammography versus Digital Mammography Plus Tomosynthesis in Breast Cancer Screening: The Oslo Tomosynthesis Screening Trial. , 2019, Radiology.

[10]  Robert M. Nishikawa,et al.  Microcalcification Classification Assisted by Content-Based Image Retrieval for Breast Cancer Diagnosis , 2007, 2007 IEEE International Conference on Image Processing.

[11]  D Koutsouris,et al.  Classification algorithms for microcalcifications in mammograms (Review). , 2006, Oncology reports.

[12]  M. Morgan,et al.  Microcalcifications in breast cancer: From pathophysiology to diagnosis and prognosis. , 2018, Biochimica et biophysica acta. Reviews on cancer.

[13]  Ervin Sejdic,et al.  Spatial indices of repolarization correlate with non-ST elevation myocardial ischemia in patients with chest pain , 2017, Medical & Biological Engineering & Computing.

[14]  S. Dudoit,et al.  Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data , 2002 .

[15]  T M Svahn,et al.  Breast tomosynthesis and digital mammography: a comparison of diagnostic accuracy. , 2012, The British journal of radiology.

[16]  Hamid Soltanian-Zadeh,et al.  Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms , 2004, Pattern Recognit..

[17]  I. Sechopoulos.  A review of breast tomosynthesis. Part I. The image acquisition process. , 2013, Medical physics.

[18]  Klaus Nordhausen,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman , 2009 .

[19]  Chein-I Chang,et al.  Classification of clustered microcalcifications using a Shape Cognitron neural network , 2003, Neural Networks.

[20]  Krzysztof J. Geras,et al.  Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives. , 2019, Radiology.

[21]  Joachim Dengler,et al.  Segmentation of microcalcifications in mammograms , 1991, IEEE Trans. Medical Imaging.

[22]  Gianpaolo Francesco Trotta,et al.  A Supervised Breast Lesion Images Classification from Tomosynthesis Technique , 2017, ICIC.

[23]  Hayit Greenspan,et al.  Multi-View Probabilistic Classification of Breast Microcalcifications , 2016, IEEE Transactions on Medical Imaging.

[24]  Heng-Da Cheng,et al.  Computer-aided detection and classification of microcalcifications in mammograms: a survey , 2003, Pattern Recognit..

[25]  Cheng Zhang,et al.  Multi‐domain features for reducing false positives in automated detection of clustered microcalcifications in digital breast tomosynthesis , 2019, Medical physics.

[26]  Robert M. Nishikawa,et al.  A study on several Machine-learning methods for classification of Malignant and benign clustered microcalcifications , 2005, IEEE Transactions on Medical Imaging.

[27]  A. Jemal,et al.  Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries , 2018, CA: a cancer journal for clinicians.

[28]  Dimitrios I. Fotiadis,et al.  Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines , 2005, Artif. Intell. Medicine.